# Copyright (c) 2021 Graphcore Ltd. All rights reserved.
# Copyright 2019 Shigeki Karita
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# This file has been modified by Graphcore Ltd.
# limitations under the License.
"""
This script has been adapted from some of the original EspNet found here:
[
    https://github.com/espnet/espnet/blob/master/espnet/nets/pytorch_backend/transformer/subsampling.py
]
Main change:
    remove the TooShortUttError class, Conv2dSubsampling6 class and Conv2dSubsampling8.

"""

import torch


class Conv2dSubsampling(torch.nn.Module):
    """Convolutional 2D subsampling (to 1/4 length).

    Args:
        idim (int): Input dimension.
        odim (int): Output dimension.
        dropout_rate (float): Dropout rate.
        pos_enc (torch.nn.Module): Custom position encoding layer.

    """

    def __init__(self, idim, odim, dropout_rate, pos_enc):
        """Construct an Conv2dSubsampling object."""
        super(Conv2dSubsampling, self).__init__()
        self.conv = torch.nn.Sequential(
            torch.nn.Conv2d(1, odim, 3, 2),
            torch.nn.ReLU(),
            torch.nn.Conv2d(odim, odim, 3, 2),
            torch.nn.ReLU(),
        )
        self.out = torch.nn.Sequential(torch.nn.Linear(odim * (((idim - 1) // 2 - 1) // 2), odim), pos_enc)

    def forward(self, x, x_mask):
        """Subsample x.

        Args:
            x (torch.Tensor): Input tensor (#batch, time, idim).
            x_mask (torch.Tensor): Input mask (#batch, 1, time).

        Returns:
            torch.Tensor: Subsampled tensor (#batch, time', odim),
                where time' = time // 4.
            torch.Tensor: Subsampled mask (#batch, 1, time'),
                where time' = time // 4.

        """
        x = x.unsqueeze(1)
        x = self.conv(x)
        b, c, t, f = x.size()
        x = self.out(x.transpose(1, 2).contiguous().view(b, t, c * f))

        if x_mask is None:
            return x, None
        return x, x_mask[:, :, :-2:2][:, :, :-2:2]